Multi-sensor-based method for early detection of bacterial wilt of tobacco
Abstract
Abstract: Tobacco is a significant economic crop in China, but it is susceptible to various diseases and insect pests, including the highly contagious tobacco bacterial wilt disease. The disease can cause severe damage with no possibility of eradication once it occurs. In this study, we collected hyperspectral and visible light data of tobacco seedlings at different stages of the disease development and compared the detection performance of the two methods. We proposed the XGBoost ensemble learning algorithm to construct a detection model for tobacco bacterial wilt disease based on the characteristic bands selected from hyperspectral data. The model achieved an accuracy of 92.20% for all samples. Additionally, an improved model Tobacco-AT was designed based on visible light images, introducing the attention mechanism with focusing function into the current popular target detection model framework, achieved high accuracy on tobacco bacterial wilt data set. Detection performance of the two methods was compared, and the results showed that the hyperspectral model had an accuracy of 69.57% on the first day after inoculation, while the accuracy of Tobacco-AT was only 54.66%. However, the accuracy of visible light based method (Tobacco-AT) was close to that of the hyperspectral based method at 85.00% and 86.36% on the third day, which demonstrates the potential of visible light technology for early detection and the possibility of being a low-cost solution.
Keywords: Tobacco bacterial wilt detection; hyperspectral imaging; deep learning; plant disease early detection; classification algorithm
DOI: 10.33440/j.ijpaa.20230601.219
Citation: Zeng X F, Li Y Y, Li J, Pu Z, Zheng L and Song P. Multi-sensor-based method for early detection of bacterial wilt of tobacco. Int J Precis Agric Aviat, 2023; 6(1): 33–43.
Full Text:
PDFReferences
André, d. S. X., Fraleon, d. A. J. C., Gonçalves, d. M. A., M, R. G., M, T. D., Reis, d. R. R., Sylvain, M., Poliane, A.-Z. Characterization of CRISPR-Cas systems in the Ralstonia solanacearum species complex. Molecular plant Pathology, 2019, 20(2). doi: 10.1111/mpp.12750
Hayward, A. C. Biology and Epidemiology of Bacterial Wilt Caused by Pseudomonas Solanacearum. Annual Review of Phytopathology, 1991, 29(1). doi: 10.1146/annurev.phyto.29.1.65
Chávez, P., Yarlequé, C., Loayza, H., Mares, V., Hancco, P., Priou, S., Márquez, M. d. P., Posadas, A., Zorogastúa, P., Flexas, J. Detection of bacterial wilt infection caused by Ralstonia solanacearum in potato (Solanum tuberosum L.) through multifractal analysis applied to remotely sensed data. Precision Agriculture, 2012, 13, 236–255. doi: 10.1007/ s11119-011-9242-5
Xie, C., Shao, Y., Li, X., He, Y., Detection of early blight and late blight diseases on tomato leaves using hyperspectral imaging. Scientific reports 2015, 5 (1), 16564, doi:10.1038/srep16564
Mahlein, A. K., Kuska, M. T., Behmann, J., Polder, G., Walter, A., Hyperspectral Sensors and Imaging Technologies in Phytopathology: State of the Art. Annu Rev Phytopathol 2018, 56, 535–558, doi: 10.1146/ annurev-phyto-080417-050100
Yang, W., Duan, L., Chen, G., Xiong, L., Liu, Q. Plant phenomics and high-throughput phenotyping: accelerating rice functional genomics using multidisciplinary technologies. Current Opinion in Plant Biology, 2013, 16(2): 180–187. doi:10.1016/j.pbi.2013.03.005
Aaron, P., Sara, P., Albert, C., Corely, H. C., Jose, D. G. I., Changying, L. High throughput phenotyping of tomato spot wilt disease in peanuts using unmanned aerial systems and multispectral imaging. IEEE Instrumentation & Measurement Magazine, 2017, 20(3): doi: 10.1109/MIM.2017.7951684
Ali, H., Lali, M. I., Nawaz, M. Z., Sharif, M., Saleem, B. A. Symptom based automated detection of citrus diseases using color histogram and textural descriptors. Computers & Electronics in Agriculture, 2017, 138(C): 92–104. doi: 10.1016/j.compag.2017.04.008
Arnal, B. J. G. An Automatic Method to Detect and Measure Leaf Disease Symptoms Using Digital Image Processing. Plant disease, 2014, 98(12). doi: 10.1094/PDIS-03-14-0290-RE
Zhang, M., Chen, T., Gu, X., Chen, D., Wang, C., Wu, W., Zhu, Q., Zhao, C. Hyperspectral remote sensing for tobacco quality estimation, yield prediction, and stress detection: A review of applications and methods. Front Plant Sci, 2023, 14, 1073346. doi: 10.3389/fpls.2023.1073346
Gu, Q., Sheng, L., Zhang, T., Lu, Y., Zhang, Z., Zheng, K., Hu, H., Zhou, H. Early detection of tomato spotted wilt virus infection in tobacco using the hyperspectral imaging technique and machine learning algorithms. Computers and Electronics in Agriculture, 2019, 167, 105066. doi: 10.1016/j.compag.2019.105066
Yusuf, B. L., He, Y. Application of hyperspectral imaging sensor to differentiate between the moisture and reflectance of healthy and infected tobacco leaves. Afr. J. Agric. Res, 2011, 6(29): 6267–6280. doi: 10.5897/AJAR11.1281
Terentev, A., Dolzhenko, V., Fedotov, A., Eremenko, D.. Current State of Hyperspectral Remote Sensing for Early Plant Disease Detection: A Review. Sensors (Basel), 2022, 22(3): 757. doi: 10.3390/s22030757
Hongyan, Z., Bingquan, C., Chu, Z., Fei, L., Linjun, J.,Yong, H. Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers. Scientific reports, 2017, 7(1). doi: 10.1038/s41598-017-04501-2
Camargo, Smith, J S. An image-processing based algorithm to automatically identify plant disease visual symptoms. Biosyst Eng, 2009. doi: 10.1016/j.biosystemseng.2008.09.030
Shi, Y., Huang, W., Luo, J., Huang, L., Zhou, X. Detection and discrimination of pests and diseases in winter wheat based on spectral indices and kernel discriminant analysis. Computers & Electronics in Agriculture, 2017, 141, 171–180. doi: 10.1016/j.compag.2017.07.019
Wang, D., Tan, X. Unsupervised Feature Learning with C-SVDDNet. 2014. doi: 10.1016/j.patcog.2016.06.001
Phadikar, S., Sil, J., Das, A. K. Feature selection by attribute clustering of infected rice plant images. International Journal of Machine Intelligence 2011, 3(2). doi: 10.9735/0975-2927.3.2.74-88
Sujatha, R., Chatterjee, J. M., Jhanjhi, N., Brohi, S. N. Performance of deep learning vs machine learning in plant leaf disease detection. Microprocessors and Microsystems, 2021, 80, 103615. doi: 10.1016/ j.micpro.2020.103615
A, G. R., B, S. S., B, J. M. M., C, W. S. L., A, J. R., B, R. E. Comparison of two aerial imaging platforms for identification of Huanglongbing-infected citrus trees. Computers and Electronics in Agriculture, 2013, 91(1): 106-115. doi: 10.1016/j.compag.2012.12.002
Liang, Q., Xiang, S., Hu, Y., Coppola, G., Zhang, D., Sun, W. PD 2 SE-Net: Computer-assisted plant disease diagnosis and severity estimation network. Computers and Electronics in Agriculture, 2019, 157, 518–529. doi:10.1016/j.compag.2019.01.034
Zeng, W., Li, M. Crop leaf disease recognition based on Self-Attention convolutional neural network. Computers and Electronics in Agriculture 2020, 172(C). doi: 10.1016/j.compag.2020.105341
Afework, Y. K., Debelee, T. G. Detection of bacterial wilt on enset crop using deep learning approach. International Journal of Engineering Research in Africa, 2020, 51, 131–146. doi: 10.4028/www.scientific.net/JERA.51.131
Huang, C., Zhang, Z., Zhang, X., Jiang, L., Hua, X., Ye, J., Yang, W., Song, P., Zhu, L. A Novel Intelligent System for Dynamic Observation of Cotton Verticillium Wilt. Plant Phenomics, 2023, 5, 0013. doi: 10.34133/plantphenomics.0013
Sutton, S. Measurement of cell concentration in suspension by optical density. Microbiology, 2006, 585, 210–8336.
Chen, T., Guestrin, C. In Xgboost: A scalable tree boosting system, Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp785–794.
Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J. Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 2021. doi: 10.48550/arXiv.2107.08430
Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W. YOLOv6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976, 2022. doi: DOI:10.48550/arXiv.2209.02976
Redmon, J., Divvala, S., Girshick, R., Farhadi, A. In You only look once: Unified, real-time object detection, Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp779–788.
Zhu, X., Lyu, S., Wang, X.,Zhao, Q. TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios, 2021. doi: 10.48550/arXiv.2108.11539
Saleem, M. H., Potgieter, J., Mahmood Arif, K. Plant disease detection and classification by deep learning. Plants (Basel), 2019, 8(11): 468. doi: 10.3390/plants8110468
Liu, S., Qi, L., Qin, H., Shi, J., Jia, J. Path Aggregation Network for Instance Segmentation. 2018 IEEE/CVF Conference on Computer Vision
and Pattern Recognition (CVPR), 2018. doi: 10.1109/CVPR.2018.00913
Feng, C., Zhong, Y., Gao, Y., Scott, M. R., Huang, W. In Tood: Task-aligned one-stage object detection, 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE Computer Society, 2021, pp3490–3499.
Ge, Z., Liu, S., Li, Z., Yoshie, O., Sun, J. In Ota: Optimal transport assignment for object detection, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp303–312.
Cen, Y., Huang, Y., Hu, S., Zhang, L., Zhang, J. Early detection of bacterial wilt in tomato with portable hyperspectral spectrometer. Remote Sensing, 2022, 14(12): 2882. doi: 10.3390/rs14122882
Golhani, K., Balasundram, S. K., Vadamalai, G., Pradhan, B. A review of neural networks in plant disease detection using hyperspectral data. Information Processing in Agriculture 2018, 5(3): 354–371. doi: 10.1016/j.inpa.2018.05.002
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.